Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

VQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Question AnsweringVQA v2
Accuracy88.1
1,165
Visual Question AnsweringVQA v2 (test-dev)
Overall Accuracy86
664
Visual Question AnsweringVQA v2 (test-std)
Accuracy86.1
466
Visual Question AnsweringVQA 2.0 (test-dev)
Accuracy86.5
337
Visual Question AnsweringVQAv2
Accuracy83.1
177
Visual Question AnsweringVQA (test-dev)
Acc (All)78.25
147
Visual Question AnsweringVQA 2.0 (val)
Accuracy (Overall)76.5
143
Visual Question AnsweringVQA v2 (test)
Accuracy86.1
131
Visual Question AnsweringVQA (test-std)
Accuracy84
110
Open-Ended Visual Question AnsweringVQA 1.0 (test-dev)
Overall Accuracy66.7
100
Visual Question AnsweringVQA v2 (val)
Accuracy86.1
99
Visual Question AnsweringVQAv2 (test-dev)
Accuracy86.1
76
Visual Question AnsweringVQAv2 (test)
VQA Accuracy79.4
72
Visual Question Answering (Multiple-choice)VQA 1.0 (test-dev)
Accuracy (All)70.04
66
Visual Question AnsweringVQA (val)
Overall Accuracy79.54
55
Open-Ended Visual Question AnsweringVQA 1.0 (test-standard)
Overall Accuracy67.36
50
Visual Question AnsweringVQA text
Accuracy82.2
48
Visual Question AnswerVQA 1.0 (test-dev)
Overall Accuracy67.42
44
Visual Question AnsweringVQA v2
Accuracy (Clean)74.5
37
Visual Question AnsweringVQA v2
Accuracy79.01
36
Visual Question AnsweringVQAv2
Accuracy54.1
36
Open-ended Visual Question AnsweringVQA (test-standard)
Accuracy (Overall)83.3
32
Visual Question AnsweringVQA v2 (std)
Accuracy84.3
31
Visual Question AnsweringVQAv2 (test-std)
Accuracy82.3
30
Visual Question AnsweringVQA v2 (dev)
Accuracy84.3
30
Showing 25 of 104 rows